Sliced Inverse Regression with Thresholding

Implements a thresholded version of the Sliced Inverse Regression method (Li, K. C. (1991) ), which allows to do variable selection.

Variable selection with Sliced Inverse Regression (SIR) thresholded

Description

This package offers an implementation of the SIR (Sliced Inverse Regression) method, along with a thresholded version of SIR that allows variable selection. Fore more information, you can check the vignette of the package on that link, and explore the code on the GitHub repository.

A paper is currently being written.

Install

From CRAN

install.packages("SIRthresholded")

From GitHub

To install the current development version from GitHub:

# install.packages("devtools")
devtools::install_github("clement-w/sirthresholded", build_vignettes = TRUE)

It is also possible to clone the repository, and install it manually (note: pandoc is required to build the vignette):

git clone [email protected]:Clement-W/SIRthresholded.git
cd SIRthresholded
R

# install.packages("devtools")
devtools::install(build_vignettes = TRUE)
library(SIRthresholded)

Access the vignette

Once that package is installed, you can access the vignette with

vignette("SIRthresholded")